Tools
Tools
Matin, Atif, Patel, Preeti and Hassan, Bilal (2026) Duration-adjusted composite metric for evaluating engagement in pre-recorded medical lecture videos. In: International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA-2026, 8 - 9 June 2026, London. (In Press)
This study presents a data-driven method for evaluating pre-recorded lecture videos in a fully online medical education programme. While video-based learning is widely used, systematic approaches to identifying underperforming content remain limited. Using interaction data from 348 lecture videos across nine modules, three engagement metrics: completion rate, time viewed, and drop-off rate were analysed. To address the confounding effect of video duration, each metric was adjusted using within-module linear regression. The resulting residuals were standardised and combined into a weighted composite engagement score, enabling ranking of videos relative to module norms. Results show that duration strongly influences raw engagement metrics, particularly time viewed, and that adjustment is necessary for meaningful comparison. The composite score identifies both high- and low-performing videos, including cases of genuine low engagement and data anomalies. Variation across modules highlights the importance of context-sensitive analysis. The method provides a practical framework for supporting evidence-based lecture improvement in online medical education.
![[thumbnail of 94_CRC.pdf]](https://repository.londonmet.ac.uk/style/images/fileicons/text.png "94_CRC.pdf")
Restricted to Repository staff only until 26 April 2027.
Download (601kB) | Request a copy
 |
View Item |